Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to the word "golden" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    singular
    -0.17
    sel
    -0.17
    ¸ı
    -0.16
    tiv
    -0.16
    ucci
    -0.16
    tics
    -0.15
    sWith
    -0.15
    tual
    -0.15
    ermann
    -0.14
    tings
    -0.14
    POSITIVE LOGITS
    rod
    0.35
     retrie
    0.32
    eye
    0.30
     Age
    0.24
     age
    0.24
    -haired
    0.24
     opportunity
    0.24
    berg
    0.24
     rule
    0.24
     Rule
    0.23
    Act Density 0.009%

    No Known Activations